notch776/law_rag_system
A corporate law RAG system with innovative retrieval and contextual strategies
Implements hybrid retrieval combining vector search (Elasticsearch with IK tokenization), BM25, and rule-based pattern matching fused via Reciprocal Rank Fusion, with BGE-reranker-large post-ranking to handle complex multi-document legal queries. Deploys a tiered context architecture using Redis for short-term dialogue caching and Neo4j graph storage for long-term history, while threshold-based context injection controls token consumption and latency. Built on FastAPI/Vue3 with WebSocket support for seamless AI-to-human agent handoff and integrates Alibaba's Qwen-Max LLM via DashScope API.
No commits in the last 6 months.
Stars
62
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/notch776/law_rag_system"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Ramseygithub/ai-legal-compliance-assistant
AI-powered legal compliance assistant for alcohol beverage pricing laws — extracts, analyzes,...
adityaprasad-sudo/ExploreSingapore
A sophisticated RAG intelligence engine for Singaporean laws, policies, and history. Comes with...
petrosrapto/PAKTON
Code for "PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements",...
Debapriya-source/nyaya-gpt
AI agent with RAG+ReAct on Indian Constitution & BNS
lixx21/legal-document-assistant
A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses...